© 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. 6-RES-JB
    11. 6482
    Prev
    Next
    INDEX
    Explanations

    expressions of surprise or emotion

    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.6.hook_resid_post_16384_anthropic_fast_lr
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.20
    0.8%
    1967
    +0.08
    0.3%
    1352
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    505
    +0.20
    0.05
    455
    +0.08
    0.04
    1352
    +0.08
    0.06
    Negative Logits
    <bos>
    -2.78
    ⓧ
    -0.80
    /***
    -0.71
     intersper
    -0.71
    <?
    -0.69
     amass
    -0.59
    /**
    -0.58
     endow
    -0.58
     banish
    -0.58
     rouse
    -0.57
    POSITIVE LOGITS
     soulign
    0.85
     nikah
    0.81
     jawa
    0.80
     Pekan
    0.79
     épu
    0.79
     Minang
    0.79
     allah
    0.79
     umo
    0.77
     Muhamma
    0.77
     lampada
    0.77
    Activations Density 1.349%

    No Known Activations