© 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. 2165
    Prev
    Next
    INDEX
    Explanations

    action directives, such as "click here" or "to read," and specific countries and medical terms

    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
    1343
    +0.11
    0.3%
    1671
    +0.09
    0.3%
    1097
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1147
    +0.11
    0.03
    1309
    +0.09
    0.02
    1671
    +0.08
    0.03
    Negative Logits
     alkoh
    -0.85
     minimalis
    -0.83
     optik
    -0.83
     vokal
    -0.81
     kosme
    -0.77
     antik
    -0.77
     Milán
    -0.75
     kompati
    -0.74
     radikal
    -0.73
     bakteri
    -0.71
    POSITIVE LOGITS
     reluct
    1.08
     affor
    1.07
     ineffec
    1.06
     impra
    1.05
     maneu
    1.03
     disagre
    1.01
     suscep
    0.98
     intersper
    0.97
     shenan
    0.97
     scrat
    0.97
    Activations Density 0.081%

    No Known Activations