© 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-2-9B
    4. Residual Stream - 16k
    5. 28-GEMMASCOPE-RES-16K
    6. 3949
    Prev
    Next
    INDEX
    Explanations

    phrases related to movement or action

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

    movement or direction

    np_acts-logits-general · gemini-2.0-flash

    verbs of motion and direction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     MenuView
    -0.40
     OFDb
    -0.38
     doubted
    -0.33
    Personendaten
    -0.32
     tarta
    -0.32
    einander
    -0.30
     hoor
    -0.30
     horen
    -0.29
    -------
    -0.29
    pushFollow
    -0.29
    POSITIVE LOGITS
    addGap
    0.56
     thither
    0.53
     away
    0.52
    Proceed
    0.49
     proceed
    0.49
     nowhere
    0.48
    getZ
    0.48
    StoryboardSegue
    0.48
    ofire
    0.47
    iastes
    0.47
    Activations Density 0.127%

    No Known Activations