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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 6-RES-JB
    11. 275
    Prev
    Next
    INDEX
    Explanations

    words related to evil and wrongdoing

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.6.hook_resid_post_16384_anthropic_fast_lr
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.17
    0.9%
    1974
    +0.11
    0.6%
    950
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    468
    +0.17
    0.02
    1974
    +0.11
    0.02
    699
    +0.09
    0.02
    Negative Logits
    <bos>
    -3.37
    /***
    -0.79
    public
    -0.76
    /*!
    -0.74
    HasColumnType
    -0.74
    AutoScaleMode
    -0.68
    <tfoot>
    -0.67
    Географи
    -0.67
     immer
    -0.65
    foreach
    -0.65
    POSITIVE LOGITS
     Minang
    1.82
     Juf
    1.70
     sappi
    1.64
     tramont
    1.62
     stockholm
    1.62
     bandung
    1.57
     wien
    1.56
     milano
    1.53
     jaya
    1.52
     frankfurt
    1.51
    Activations Density 0.127%

    No Known Activations