© 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. 536
    Prev
    Next
    INDEX
    Explanations

    Institute and College names

    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
    +0.07
    0.3%
    466
    +0.07
    0.3%
    891
    +0.06
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    552
    +0.07
    0.07
    1385
    +0.07
    0.10
    1870
    +0.06
    0.01
    Negative Logits
    <bos>
    -1.48
    ⓧ
    -1.19
    /**
    -1.19
    <?
    -1.10
    
    -1.09
    /*
    -0.98
    <?
    -0.88
     endow
    -0.80
    #![
    -0.68
     springfox
    -0.63
    POSITIVE LOGITS
     Minang
    1.20
     lele
    1.18
     bandung
    1.12
     jaya
    1.12
     Jambi
    1.12
     jawa
    1.10
    mavi
    1.07
     seksi
    1.06
     valla
    1.05
     maroc
    1.04
    Activations Density 1.822%

    No Known Activations