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. 3218
    Prev
    Next
    INDEX
    Explanations

    terms related to legal and regulatory aspects of gun ownership

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

    Follows nouns related to professions or legal issues

    np_acts-logits-general · gemini-2.0-flash

    legal, medical, and financial terms

    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
    onges
    -0.41
    Erstellt
    -0.40
    исленность
    -0.37
    jago
    -0.37
    inescence
    -0.36
    Modifications
    -0.36
    adag
    -0.35
     Tenemos
    -0.35
     niềm
    -0.35
    Dimensioni
    -0.35
    POSITIVE LOGITS
     AssemblyProduct
    0.52
     Autorizaciones
    0.50
    Aholisi
    0.48
    SharedCtor
    0.48
    </tfoot>
    0.43
    OOTDTY
    0.41
    TokenNameLBRACE
    0.41
    ExtendWith
    0.40
    Insn
    0.40
    ktop
    0.40
    Activations Density 1.314%

    No Known Activations