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

    Neuronpedia

    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. 1965
    Prev
    Next
    INDEX
    Explanations

    positive experiences and interactions in a social or communal setting

    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
    1823
    +0.09
    0.2%
    1533
    +0.08
    0.2%
    599
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1823
    +0.09
    0.03
    940
    +0.08
    0.03
    1533
    +0.08
    0.01
    Negative Logits
     anhyd
    -0.80
     Cfr
    -0.76
     alberto
    -0.75
     Ibidem
    -0.74
     loren
    -0.72
     jorge
    -0.72
     MATHEMAT
    -0.71
     AGRIC
    -0.71
     surfact
    -0.69
     stefan
    -0.68
    POSITIVE LOGITS
    <bos>
    1.32
    aderie
    0.67
     atmosfera
    0.67
     welcoming
    0.65
     friendly
    0.61
     camaraderie
    0.61
     atmosphere
    0.61
    kindness
    0.58
     kindness
    0.58
     supportive
    0.56
    Activations Density 0.380%

    No Known Activations