© 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. 476
    Prev
    Next
    INDEX
    Explanations

    copyright information

    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
    +0.14
    0.7%
    783
    +0.06
    0.3%
    1974
    +0.06
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    297
    +0.14
    0.07
    757
    +0.06
    0.07
    1974
    +0.06
    0.06
    Negative Logits
    <bos>
    -1.70
    <?
    -0.95
    ⓧ
    -0.95
    
    -0.81
    /**
    -0.76
     continue
    -0.75
    #
    -0.73
    public
    -0.73
    /*
    -0.73
    }{||
    -0.71
    POSITIVE LOGITS
     accla
    2.15
     maneu
    2.15
     affor
    2.06
     stockholm
    2.02
     Juf
    2.01
     increa
    1.97
     guarante
    1.96
     strick
    1.96
     véhic
    1.92
     ?...
    1.89
    Activations Density 0.171%

    No Known Activations