© 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. 14158
    Prev
    Next
    INDEX
    Explanations

    phrases related to historical or technical information

    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
    58
    +0.13
    0.4%
    453
    +0.12
    0.4%
    1870
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    58
    +0.13
    0.03
    1618
    +0.12
    0.02
    1415
    +0.10
    0.02
    Negative Logits
     no
    -0.56
     far
    -0.54
     hints
    -0.51
     spare
    -0.50
     most
    -0.49
    stdbool
    -0.48
     K
    -0.48
     Q
    -0.48
    organize
    -0.48
     Compare
    -0.48
    POSITIVE LOGITS
     lapto
    1.25
     silikon
    1.23
     reger
    1.22
     dises
    1.17
     cyr
    1.16
     kafe
    1.14
     etui
    1.13
    fordable
    1.13
     soggior
    1.11
     ciga
    1.11
    Activations Density 0.053%

    No Known Activations