© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 6056
    Prev
    Next
    INDEX
    Explanations

    symbols and characters used in text formatting or coding languages

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

    Square brackets, parenthesis, and following letters

    np_acts-logits-general · gemini-2.0-flash

    bracketed words

    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
     prevented
    -0.41
    Ligações
    -0.40
     afectado
    -0.39
     Aufenthalts
    -0.38
    <bos>
    -0.38
     afectadas
    -0.38
     esclavos
    -0.36
     thwarted
    -0.36
     detuvo
    -0.35
     treated
    -0.35
    POSITIVE LOGITS
    tagHelperRunner
    0.53
    ActionCreators
    0.50
     referenties
    0.49
    SequentialGroup
    0.49
     kasarigan
    0.48
    BagLayout
    0.48
    BagConstraints
    0.47
    ValueStyle
    0.46
    vogel
    0.44
    idavit
    0.44
    Activations Density 0.638%

    No Known Activations