Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 9092
    Prev
    Next
    INDEX
    Explanations

    terms related to limitations and constraints

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

    words and phrases related to limitations, constraints, or restrictions.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rungsseite
    -0.57
     disambiguazione
    -0.46
    verwijspagina
    -0.44
    marvin
    -0.44
    AndEndTag
    -0.44
    EndContext
    -0.43
    קישורים
    -0.42
     mergeFrom
    -0.42
    mergeFrom
    -0.42
    WebServlet
    -0.42
    POSITIVE LOGITS
     limitations
    2.50
     restrictions
    2.48
     limitation
    2.33
     restriction
    2.27
     constraints
    2.25
     Restrictions
    2.06
    restrictions
    2.05
    limitations
    2.03
     restricted
    2.02
     Limitations
    2.02
    Activations Density 1.011%

    No Known Activations