© 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. 0-RES-JB
    6. 548
    Prev
    Next
    INDEX
    Explanations

    mentions of educational related terms, specifically focusing on tuition and tutoring

    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
    1870
    +0.07
    0.3%
    50
    +0.07
    0.3%
    1705
    +0.06
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    492
    +0.07
    0.03
    1150
    +0.07
    0.02
    77
    +0.06
    0.02
    Negative Logits
    <bos>
    -1.45
    ⓧ
    -0.72
     put
    -0.70
    ,
    -0.68
     also
    -0.67
     got
    -0.65
     keep
    -0.63
     ask
    -0.61
     asked
    -0.61
     be
    -0.61
    POSITIVE LOGITS
     bandung
    1.86
     lele
    1.73
     maroc
    1.69
     Minang
    1.69
     jaya
    1.65
     saar
    1.64
     maneu
    1.61
     tramont
    1.52
     affor
    1.51
     napoli
    1.51
    Activations Density 0.089%

    No Known Activations