© 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. 6477
    Prev
    Next
    INDEX
    Explanations

    text related to personal experiences and expressing opinions or conclusions

    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
    +0.22
    1.2%
    1096
    +0.12
    0.7%
    90
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    32
    +0.22
    0.08
    1096
    +0.12
    0.08
    1392
    +0.12
    0.08
    Negative Logits
    <bos>
    -3.49
    <>
    -0.69
    public
    -0.66
    ///**
    -0.66
    Vegeu
    -0.66
    parsedMessage
    -0.64
    /**
    -0.63
    सं
    -0.62
    /***
    -0.61
    },{
    -0.61
    POSITIVE LOGITS
     stockholm
    1.69
     increa
    1.48
     maneu
    1.44
     beverly
    1.38
     philanth
    1.37
     fortn
    1.37
     sovere
    1.37
     embodi
    1.37
     volunte
    1.35
     affor
    1.35
    Activations Density 0.385%

    No Known Activations