© 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. 10-RES-JB
    11. 608
    Prev
    Next
    INDEX
    Explanations

    instances of the word "prepare" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.10.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    chanind/openwebtext-gemma
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    standard
    Context Size
    1,024
    Dataset
    ctigges/openwebtext-gemma-1024-cl
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.26
    1.4%
    1573
    +0.09
    0.5%
    506
    +0.08
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1573
    +0.26
    0.02
    75
    +0.09
    0.02
    890
    +0.08
    0.02
    Negative Logits
    <bos>
    -2.74
    ⓧ
    -0.76
    Vegeu
    -0.73
     catch
    -0.65
     caught
    -0.60
    catch
    -0.59
     ruled
    -0.58
    echo
    -0.58
    Вз
    -0.57
    uint
    -0.57
    POSITIVE LOGITS
     wien
    1.56
     maneu
    1.50
     milf
    1.47
     bandung
    1.46
     ibiza
    1.46
     wikihow
    1.44
     lara
    1.44
     increa
    1.44
     yong
    1.43
     excru
    1.42
    Activations Density 0.041%

    No Known Activations