© 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
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 860
    Prev
    Next
    INDEX
    Explanations

    keywords related to financial accounting and numbers

    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
    952
    +0.08
    0.2%
    876
    +0.08
    0.2%
    585
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    952
    +0.08
    0.03
    1207
    +0.08
    0.03
    1555
    +0.07
    0.04
    Negative Logits
     Alcalde
    -0.55
     pecuni
    -0.53
     betek
    -0.53
     gmbh
    -0.48
     spied
    -0.44
     Bár
    -0.43
     Wtf
    -0.43
    ;++
    -0.43
     Mónica
    -0.43
    indsay
    -0.42
    POSITIVE LOGITS
     factors
    0.63
     factoring
    0.58
     factores
    0.56
     chert
    0.55
     factor
    0.54
     accounting
    0.54
     allowances
    0.53
    собенности
    0.53
     luat
    0.53
     prenota
    0.52
    Activations Density 0.336%

    No Known Activations