© 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. 14635
    Prev
    Next
    INDEX
    Explanations

    historical and technical details in texts

    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
    1013
    +0.09
    0.2%
    297
    +0.08
    0.2%
    776
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1561
    +0.09
    0.03
    1881
    +0.08
    0.04
    1818
    +0.08
    0.04
    Negative Logits
    RuleContext
    -0.69
    disposing
    -0.63
    TypedDataSet
    -0.62
    featureID
    -0.61
    CppMethod
    -0.60
    styleType
    -0.58
     nahilalakip
    -0.58
     تانيه
    -0.56
    SharedCtor
    -0.56
    ItemLayout
    -0.56
    POSITIVE LOGITS
     impra
    1.18
     impractica
    1.14
     unve
    1.11
     cytoplas
    1.09
     increa
    1.09
     wikihow
    1.08
     tranf
    1.07
     attemp
    1.06
     resear
    1.06
     perfon
    1.05
    Activations Density 0.502%

    No Known Activations