© 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. 13695
    Prev
    Next
    INDEX
    Explanations

    key phrases related to social, political, and academic discussions

    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
    1870
    +0.10
    0.3%
    1978
    +0.08
    0.2%
    994
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    284
    +0.10
    0.06
    2010
    +0.08
    0.05
    1657
    +0.08
    0.04
    Negative Logits
     Intere
    -1.15
     depic
    -1.14
     Confe
    -1.10
     volunte
    -1.09
     reluct
    -1.09
     Manufact
    -1.08
    timately
    -1.07
     inev
    -1.06
     encomp
    -1.05
     guarante
    -1.05
    POSITIVE LOGITS
     into
    0.92
    <bos>
    0.83
     onto
    0.82
     beginnetje
    0.79
    RegressionTest
    0.71
     Paglinawan
    0.69
    into
    0.69
    FunctionFlags
    0.68
    MigrationBuilder
    0.67
     velkommen
    0.66
    Activations Density 0.417%

    No Known Activations