© 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
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 429
    Prev
    Next
    INDEX
    Explanations

    references to allegations of serious crimes and legal proceedings involving multiple individuals

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

    detailed factual descriptions of specific incidents or allegations with supporting details.

    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
     мәкал
    -0.49
     hiszen
    -0.44
    ябре
    -0.40
     sors
    -0.39
    gól
    -0.39
    kháu
    -0.38
     anse
    -0.38
    tagHelperRunner
    -0.37
    доб
    -0.37
     CURIAM
    -0.36
    POSITIVE LOGITS
     supposedly
    3.16
     allegedly
    3.14
     supuestamente
    2.80
     alleged
    2.72
     purported
    2.72
    supposed
    2.58
     supposed
    2.52
     reportedly
    2.30
     angeb
    2.19
    alleg
    2.17
    Activations Density 1.332%

    No Known Activations