© 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. 6446
    Prev
    Next
    INDEX
    Explanations

    references to specific names, locations, organizations, and events, potentially related to historical or cultural context

    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
    +0.41
    2.6%
    2019
    +0.05
    0.3%
    381
    +0.05
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1108
    +0.41
    0.21
    626
    +0.05
    0.20
    1073
    +0.05
    0.19
    Negative Logits
    <bos>
    -2.16
    ⓧ
    -0.84
    public
    -0.78
    ,
    -0.72
    .
    -0.71
     promote
    -0.70
     expand
    -0.69
     put
    -0.69
    /**
    -0.69
     continue
    -0.69
    POSITIVE LOGITS
     maneu
    2.42
     affor
    2.35
     accla
    2.30
     increa
    2.29
     wien
    2.29
     emphat
    2.24
     ?...
    2.23
     effe
    2.19
     impra
    2.17
     stockholm
    2.13
    Activations Density 1.493%

    No Known Activations