Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 0-RES-JB
    6. 310
    Prev
    Next
    INDEX
    Explanations

    references to governmental or legal entities and events

    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
    1323
    +0.08
    0.3%
    50
    +0.08
    0.3%
    1103
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1587
    +0.08
    0.03
    785
    +0.08
    0.03
    1770
    +0.07
    0.03
    Negative Logits
    <bos>
    -1.55
    
    
    -0.84
    /**
    -0.75
     again
    -0.74
     earn
    -0.74
     promote
    -0.74
     immer
    -0.73
    /**
    -0.73
    /*
    -0.73
    public
    -0.72
    POSITIVE LOGITS
     Juf
    2.15
     accla
    1.98
     véhic
    1.98
     maneu
    1.92
     affor
    1.91
     Keny
    1.89
     marseille
    1.86
     stockholm
    1.84
     hcm
    1.84
     vété
    1.84
    Activations Density 0.070%

    No Known Activations