© 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. 3455
    Prev
    Next
    INDEX
    Explanations

    mentions of legal proceedings involving questioning and investigation

    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
    1978
    +0.09
    0.3%
    1166
    +0.08
    0.2%
    1224
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    284
    +0.09
    0.05
    1285
    +0.08
    0.05
    1166
    +0.08
    0.06
    Negative Logits
    UnusedPrivate
    -0.51
    donc
    -0.48
    Avez
    -0.46
    waltung
    -0.45
     betweenstory
    -0.43
     Lettre
    -0.43
    ajur
    -0.43
     Lég
    -0.42
     MediatR
    -0.42
    gigabyte
    -0.41
    POSITIVE LOGITS
     stik
    0.61
     plak
    0.59
     pranzo
    0.59
     skoro
    0.59
     vermelhas
    0.56
     affari
    0.55
     compleanno
    0.52
     vacanza
    0.52
     maske
    0.52
     spesifik
    0.51
    Activations Density 0.590%

    No Known Activations