© 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
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 0-RES-JB
    6. 540
    Prev
    Next
    INDEX
    Explanations

    words related to file management and technology

    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
    169
    +0.08
    0.3%
    650
    +0.07
    0.2%
    1272
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1340
    +0.08
    0.02
    1056
    +0.07
    0.03
    1362
    +0.07
    0.03
    Negative Logits
    <?
    -0.67
     springfox
    -0.65
     serce
    -0.63
    /**
    -0.57
    harmed
    -0.56
     overthrown
    -0.56
    
    
    -0.54
    /*
    -0.54
     miłość
    -0.53
     assassinated
    -0.53
    POSITIVE LOGITS
     Fre
    2.36
    Fre
    2.28
     fre
    2.28
    fre
    1.94
     FRE
    1.76
    FRE
    1.55
     Fré
    1.04
     Freem
    1.03
     Freed
    0.93
     délib
    0.90
    Activations Density 0.196%

    No Known Activations