© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 5864
    Prev
    Next
    INDEX
    Explanations

    reference to a person named Collins

    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
    1618
    +0.16
    0.8%
    544
    +0.15
    0.7%
    1133
    +0.14
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    981
    +0.16
    0.06
    1177
    +0.15
    0.03
    227
    +0.14
    0.06
    Negative Logits
    vaného
    -0.54
    vanou
    -0.54
    Tracce
    -0.52
    ApiModel
    -0.48
    TableBody
    -0.48
    vaných
    -0.47
    IZONT
    -0.46
    usermodel
    -0.46
     DIEGO
    -0.44
    ModelMap
    -0.44
    POSITIVE LOGITS
     apprehen
    0.85
     gaily
    0.82
     indescri
    0.80
     unspeak
    0.76
     vainly
    0.76
     invin
    0.74
     intersper
    0.73
     plenti
    0.73
     Collins
    0.73
     impelled
    0.71
    Activations Density 0.397%

    No Known Activations