© 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. 13753
    Prev
    Next
    INDEX
    Explanations

    phrases related to defining the scope and methods of a specific topic

    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
    1810
    +0.15
    0.6%
    1757
    +0.15
    0.6%
    2004
    +0.15
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1810
    +0.15
    0.02
    2004
    +0.15
    0.02
    1218
    +0.15
    0.02
    Negative Logits
     PLWABN
    -0.49
     ModelRenderer
    -0.49
    Personendaten
    -0.46
    columnNumber
    -0.45
     Савезне
    -0.45
    ferrer
    -0.44
    mored
    -0.44
     najbolj
    -0.44
     NUKAT
    -0.44
    TypedDataSet
    -0.44
    POSITIVE LOGITS
     Scope
    1.42
     scope
    1.40
     scopes
    1.39
    scope
    1.30
    Scope
    1.20
     scoped
    1.16
     SCOPE
    1.14
    scopes
    1.11
    Scopes
    1.09
     Sco
    1.08
    Activations Density 0.072%

    No Known Activations