© 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. 11753
    Prev
    Next
    INDEX
    Explanations

    numerical values or records

    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
    1575
    +0.14
    0.5%
    1978
    +0.11
    0.4%
    555
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1435
    +0.14
    0.06
    382
    +0.11
    0.05
    667
    +0.10
    0.05
    Negative Logits
    Poznám
    -0.59
    benhavn
    -0.55
    Fordítás
    -0.55
    Odpo
    -0.54
    ztő
    -0.54
     sacro
    -0.53
    Beskrivning
    -0.51
    solicited
    -0.51
     smrti
    -0.51
     isSuccess
    -0.50
    POSITIVE LOGITS
     muna
    0.84
     hina
    0.78
     alip
    0.77
     guma
    0.74
     kasa
    0.71
     duk
    0.70
     bayan
    0.69
     kani
    0.67
     tuta
    0.66
     amma
    0.66
    Activations Density 0.182%

    No Known Activations