© 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 - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 5054
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to data representation and specifications

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

    technical specification and representation

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    Bibliograf
    -0.37
    tvguidetime
    -0.36
    Autoritní
    -0.36
    SharedCtor
    -0.36
     meas
    -0.35
     allAfrica
    -0.35
     indisponible
    -0.35
    SOUNDBITE
    -0.34
     mesure
    -0.34
    Notae
    -0.33
    POSITIVE LOGITS
    NameInMap
    0.50
    lark
    0.46
     représentation
    0.44
     Representing
    0.44
    istoitu
    0.42
     ErrIntOverflow
    0.42
    튿
    0.42
    format
    0.42
    seamnă
    0.41
     sekali
    0.41
    Activations Density 0.308%

    No Known Activations