© 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. 0-RES-JB
    11. 520
    Prev
    Next
    INDEX
    Explanations

    terms related to medical conditions, diagnoses, and treatments

    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.0.hook_resid_post_16384_anthropic
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.11
    0.7%
    1870
    +0.04
    0.2%
    1978
    +0.03
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1385
    +0.11
    0.14
    1870
    +0.04
    0.01
    1253
    +0.03
    0.08
    Negative Logits
    <bos>
    -1.55
    ⓧ
    -1.17
    
    -1.12
    /**
    -1.10
    <?
    -1.07
    /*
    -0.99
    /***
    -0.93
    <?
    -0.86
    public
    -0.77
    /*++
    -0.75
    POSITIVE LOGITS
     wien
    1.72
     aen
    1.62
     maroc
    1.60
     lele
    1.60
     meis
    1.59
     stockholm
    1.58
     franz
    1.57
     fta
    1.54
     „,
    1.54
     sappi
    1.53
    Activations Density 2.356%

    No Known Activations