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-2-9B
    4. Residual Stream - 16k
    5. 0-GEMMASCOPE-RES-16K
    6. 8522
    Prev
    Next
    INDEX
    Explanations

    references to personal experiences and personal data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/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.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IntoConstraints
    -0.72
    AutoField
    -0.68
     contextLoads
    -0.68
    RuleContext
    -0.67
    principalColumn
    -0.66
    AnimationsModule
    -0.66
    ]")]
    -0.62
    Personendaten
    -0.61
    RTSC
    -0.60
    MigrationBuilder
    -0.60
    POSITIVE LOGITS
     personal
    1.25
     Personal
    1.04
    Personal
    1.02
     PERSONAL
    1.00
    personal
    0.99
     personally
    0.91
     Pick
    0.89
    PERSONAL
    0.84
    picker
    0.81
    pick
    0.80
    Activations Density 0.218%

    No Known Activations