© 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. 15-GEMMASCOPE-RES-16K
    6. 1865
    Prev
    Next
    INDEX
    Explanations

    questions and expressions of uncertainty or decision-making

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <bos>
    -0.51
    S
    -0.46
     ~
    -0.46
     примеру
    -0.43
    )
    -0.43
    ]])
    -0.41
    HasForeignKey
    -0.41
    ViewChild
    -0.41
    jski
    -0.41
    ~
    -0.40
    POSITIVE LOGITS
    happens
    0.76
     *++
    0.75
     händer
    0.74
     happens
    0.73
     ELSE
    0.73
    extAlignment
    0.72
     happened
    0.72
     happening
    0.72
    Čo
    0.71
     estekak
    0.70
    Activations Density 0.178%

    No Known Activations