© 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
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 1902
    Prev
    Next
    INDEX
    Explanations

    descriptive details and imagery related to a specific location

    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
    906
    +0.16
    0.5%
    939
    +0.14
    0.4%
    1013
    +0.14
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    939
    +0.16
    0.08
    1533
    +0.14
    0.01
    964
    +0.14
    0.04
    Negative Logits
     shenan
    -1.32
     philanth
    -1.14
     hentai
    -1.11
     vagu
    -1.11
     accla
    -1.09
     intersper
    -1.09
     apprehen
    -1.08
     reluct
    -1.06
     unspeak
    -1.06
     disagre
    -1.05
    POSITIVE LOGITS
     سكانية
    0.63
     contrast
    0.58
     inhabitants
    0.58
     streets
    0.58
    المكان
    0.57
     Walkover
    0.56
     neighborhoods
    0.56
    iastes
    0.56
     everywhere
    0.55
    wohner
    0.55
    Activations Density 0.959%

    No Known Activations