© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 11299
    Prev
    Next
    INDEX
    Explanations

    references to legal and political topics, particularly related to laws and regulations, government actions, and social issues

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1919
    +0.13
    0.4%
    674
    +0.11
    0.3%
    1978
    +0.11
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1919
    +0.13
    0.09
    1415
    +0.11
    0.05
    1690
    +0.11
    0.05
    Negative Logits
     }^{(
    -0.48
    Matériel
    -0.47
    InitStruct
    -0.47
     contextLoads
    -0.47
    Millan
    -0.47
     <<<<<<<<<<<<<<
    -0.45
    Grath
    -0.45
    ienki
    -0.44
     FormsModule
    -0.44
    COHOL
    -0.44
    POSITIVE LOGITS
     indestru
    0.58
     shenan
    0.56
     affor
    0.55
     resurre
    0.55
     coerci
    0.54
     aze
    0.54
     crossfit
    0.54
     resear
    0.54
     impra
    0.53
     disad
    0.53
    Activations Density 0.303%

    No Known Activations