© 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. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 4-GEMMASCOPE-RES-16K
    11. 10762
    Prev
    Next
    INDEX
    Explanations

    file paths and related syntax in code snippets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ält
    -0.69
    pless
    -0.64
     Jacobs
    -0.62
    JsonIgnore
    -0.62
    3
    -0.61
    logical
    -0.60
     البي
    -0.59
    ppelt
    -0.59
    cerely
    -0.58
    òi
    -0.58
    POSITIVE LOGITS
     '"
    1.36
    ='"
    1.33
    '"
    1.24
    ('"
    1.24
    ("'"
    1.18
    .'"
    1.10
    ,'"
    1.05
    ('../../../
    0.95
     '../../../
    0.90
    ="'
    0.88
    Activations Density 0.232%

    No Known Activations