© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 66211
    Prev
    Next
    INDEX
    Explanations

    phrases related to the dissemination of information and improving understanding

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

    informing actions or beliefs

    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
    AppMethodBeat
    -0.40
     eventdata
    -0.35
     miniaturka
    -0.34
    timewa
    -0.34
    converting
    -0.32
    saco
    -0.32
     Assignee
    -0.32
     comigo
    -0.31
     rivales
    -0.31
     vantagens
    -0.31
    POSITIVE LOGITS
     informed
    0.73
     Informed
    0.69
    脚注の使い方
    0.68
    Informed
    0.66
     informs
    0.65
     inform
    0.65
     inspired
    0.64
    informed
    0.63
     informing
    0.62
     inspirado
    0.60
    Activations Density 0.032%

    No Known Activations