© 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. 6-RES-JB
    6. 312
    Prev
    Next
    INDEX
    Explanations

    mentions of educational institutions and professional roles

    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
    +0.18
    0.6%
    227
    +0.10
    0.4%
    814
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    905
    +0.18
    0.04
    954
    +0.10
    0.04
    782
    +0.08
    0.04
    Negative Logits
    <bos>
    -1.45
    ⓧ
    -0.83
     springfox
    -0.72
     naudoti
    -0.71
     įsi
    -0.65
     overcrow
    -0.65
    <?
    -0.62
     nė
    -0.62
    
    
    -0.61
     thicken
    -0.61
    POSITIVE LOGITS
     Mejía
    0.86
     Khart
    0.84
     Minang
    0.82
     Ribera
    0.81
    emmel
    0.80
     Bahía
    0.80
     Meksi
    0.76
     Cár
    0.76
     Mentre
    0.76
     véhic
    0.76
    Activations Density 0.404%

    No Known Activations