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-IT
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 6987
    Prev
    Next
    INDEX
    Explanations

    scientific references to hormone levels and their effects in a medical context

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

    Followed by words like "called", "changes", "cause", or "of"

    np_acts-logits-general · gemini-2.0-flash

    cause cancer

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Personendaten
    -0.64
    PreExecute
    -0.59
     desmotivaciones
    -0.56
     głowy
    -0.54
    ReusableCell
    -0.54
    IsContent
    -0.54
     kasarigan
    -0.54
    RegressionTest
    -0.52
    migrationBuilder
    -0.52
     sanitarios
    -0.51
    POSITIVE LOGITS
     '\\;'
    0.35
     dig
    0.34
     SAC
    0.33
    nings
    0.33
     emb
    0.32
    alfa
    0.32
    DCHECK
    0.31
    {{/
    0.30
     Creature
    0.30
     armb
    0.30
    Activations Density 1.408%

    No Known Activations