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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 11586
    Prev
    Next
    INDEX
    Explanations

    comments and interactions related to online platforms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    +:+
    -0.55
     hObject
    -0.55
    .*")]
    -0.55
    principalTable
    -0.53
    ="@+
    -0.52
    NamedQueries
    -0.52
    StoryboardSegue
    -0.51
    Ӕ
    -0.50
    ⟬
    -0.50
     jsPsych
    -0.50
    POSITIVE LOGITS
     auroit
    0.51
     pouvoit
    0.46
     avoient
    0.46
    volmente
    0.45
    fahrens
    0.40
    farwyddwr
    0.39
     feroit
    0.38
     dioses
    0.37
     étoit
    0.37
    igreja
    0.37
    Activations Density 1.303%

    No Known Activations