© 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. 650
    Prev
    Next
    INDEX
    Explanations

    references to a specific technical process or legal term known as "induction" in a text

    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
    316
    +0.10
    0.3%
    1178
    +0.10
    0.3%
    528
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1363
    +0.10
    0.03
    184
    +0.10
    0.01
    690
    +0.07
    0.03
    Negative Logits
    Questão
    -0.55
     Rail
    -0.55
    ಓ
    -0.54
     Christ
    -0.54
    public
    -0.54
    Özel
    -0.54
    Christ
    -0.54
    SharedDtor
    -0.53
    dev
    -0.53
    Ві
    -0.53
    POSITIVE LOGITS
     Induction
    1.93
     induction
    1.89
     Dedu
    1.81
    induction
    1.79
     deduction
    1.78
     induct
    1.74
     deductions
    1.69
    Induction
    1.69
     deduct
    1.51
    Dedu
    1.47
    Activations Density 0.286%

    No Known Activations