© 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. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 4-GEMMASCOPE-RES-16K
    6. 2756
    Prev
    Next
    INDEX
    Explanations

    structured data references within programming and database contexts

    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
    Архівовано
    -0.72
    ReusableCell
    -0.71
    NewUrlParser
    -0.68
    ."</
    -0.65
    istoitu
    -0.63
    Примітки
    -0.63
    ."],
    -0.63
     }}"></
    -0.62
    ]**
    -0.62
    ."]
    -0.61
    POSITIVE LOGITS
    onViewCreated
    0.62
    ########.
    0.53
     ControllerBase
    0.51
     Presidencia
    0.47
     bouche
    0.47
    .*")]
    0.42
     phép
    0.42
    setFill
    0.42
     suya
    0.41
     intStringLen
    0.41
    Activations Density 0.578%

    No Known Activations