© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 0-RES-JB
    11. 116
    Prev
    Next
    INDEX
    Explanations

    mentions of specific grades in a school setting

    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
    82
    +0.08
    0.3%
    795
    +0.08
    0.3%
    50
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1354
    +0.08
    0.03
    1377
    +0.08
    0.03
    1421
    +0.08
    0.03
    Negative Logits
    <bos>
    -0.88
    public
    -0.64
    //
    -0.62
    -0.61
    /*
    -0.60
     continue
    -0.59
     be
    -0.58
    usercontent
    -0.57
     lập
    -0.56
    ,
    -0.56
    POSITIVE LOGITS
     grade
    2.58
     Grade
    2.43
     grades
    2.37
     Grades
    2.28
    Grade
    2.27
    grade
    2.21
     GRADE
    2.19
    Grades
    2.02
    grades
    1.96
     grading
    1.78
    Activations Density 0.157%
    No Known Activations