© 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. 5991
    Prev
    Next
    INDEX
    Explanations

    situations involving confrontation and acceptance of decisions

    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
    674
    +0.22
    0.7%
    1978
    +0.16
    0.5%
    1438
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1438
    +0.22
    0.05
    1041
    +0.16
    0.04
    1265
    +0.12
    0.04
    Negative Logits
     increa
    -1.79
     maneu
    -1.67
     affor
    -1.66
     inev
    -1.65
     volunte
    -1.63
     ?...
    -1.63
     effe
    -1.62
     stockholm
    -1.62
     guarante
    -1.61
     secon
    -1.61
    POSITIVE LOGITS
    <bos>
    1.48
     you
    1.02
     he
    0.92
     she
    0.89
     we
    0.88
     they
    0.84
     I
    0.81
     my
    0.79
    you
    0.76
     somebody
    0.74
    Activations Density 0.449%

    No Known Activations