© 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. 13799
    Prev
    Next
    INDEX
    Explanations

    mentions of speech and language rehabilitation or improvement

    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
    394
    +0.17
    0.7%
    1224
    +0.14
    0.5%
    1870
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1314
    +0.17
    0.11
    678
    +0.14
    0.10
    137
    +0.13
    0.13
    Negative Logits
    SneakyThrows
    -0.50
    testng
    -0.50
    GraphicsUnit
    -0.48
    AxisAlignment
    -0.47
    ValueStyle
    -0.47
    :['
    -0.45
    kloped
    -0.45
    scalatest
    -0.45
    .='
    -0.45
     etc
    -0.44
    POSITIVE LOGITS
     canel
    0.94
     palio
    0.91
     broderie
    0.86
     tanga
    0.83
     napoli
    0.81
     milano
    0.77
     cioc
    0.76
     hcm
    0.76
     mallorca
    0.75
     dora
    0.75
    Activations Density 4.740%

    No Known Activations