© 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. 453
    Prev
    Next
    INDEX
    Explanations

    information related to events and activities happening at a large convention and specific related details about different topics

    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
    +0.21
    1.1%
    2019
    +0.09
    0.5%
    1510
    +0.06
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1338
    +0.21
    0.10
    1826
    +0.09
    0.09
    1382
    +0.06
    0.09
    Negative Logits
    <bos>
    -2.64
    
    -1.24
    ⓧ
    -1.15
    /**
    -1.09
    <?
    -1.09
    <?
    -0.97
    /***
    -0.91
    /*
    -0.90
    <!--
    -0.82
    /*++
    -0.74
    POSITIVE LOGITS
     maneu
    1.33
     stockholm
    1.27
     accla
    1.19
     wien
    1.15
     impra
    1.14
     eiffel
    1.13
     affor
    1.12
     lamborghini
    1.10
     exorbit
    1.08
     excru
    1.06
    Activations Density 0.374%

    No Known Activations