© 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-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 13730
    Prev
    Next
    INDEX
    Explanations

    dialogue interaction involving scolding or reprimanding someone

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    2019
    +0.15
    0.5%
    1535
    +0.15
    0.5%
    382
    +0.14
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    382
    +0.15
    0.07
    509
    +0.15
    0.06
    1533
    +0.14
    0.03
    Negative Logits
     guarante
    -2.43
     increa
    -2.40
     affor
    -2.37
     emphat
    -2.32
     encomp
    -2.28
     maneu
    -2.22
     reluct
    -2.22
     strick
    -2.21
     inev
    -2.20
     disagre
    -2.19
    POSITIVE LOGITS
    <eos>
    0.96
     She
    0.87
     He
    0.87
     But
    0.83
    ↵↵
    0.81
     he
    0.80
     So
    0.80
     she
    0.79
    XmlSchema
    0.78
    ↵
    0.77
    Activations Density 0.286%

    No Known Activations