Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 3196
    Prev
    Next
    INDEX
    Explanations

    references to tasks and task-related actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "Task" and related actions/parameters

    np_acts-logits-general · gemini-2.0-flash

    task action or parameter

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/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.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Jefus
    -0.78
     Majefty
    -0.74
     myſelf
    -0.72
    ︎
    -0.72
     Cleopatra
    -0.71
    Apre
    -0.70
    vea
    -0.69
    μερα
    -0.69
     Marac
    -0.69
     poffible
    -0.68
    POSITIVE LOGITS
     tasks
    1.69
     task
    1.56
    tasks
    1.52
     Tasks
    1.52
    Tasks
    1.49
     Task
    1.47
     TASK
    1.44
    getTask
    1.41
    TASK
    1.37
    Task
    1.36
    Activations Density 0.053%

    No Known Activations