© 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
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 9491
    Prev
    Next
    INDEX
    Explanations

    terms related to online dating services

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

    conditional and explanatory clauses, particularly those introducing stipulations or logical consequences.

    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
    inerja
    -0.60
     mauva
    -0.54
     Spitze
    -0.54
     filles
    -0.53
     Geduld
    -0.52
     Stoff
    -0.52
    følgelig
    -0.50
     Mejía
    -0.49
     Decke
    -0.49
     Strecke
    -0.49
    POSITIVE LOGITS
    ="@+
    0.49
     EdgeInsets
    0.43
     StatelessWidget
    0.41
    BASEPATH
    0.41
    XmlAccessType
    0.41
    XmlAccessorType
    0.41
    AnchorStyles
    0.40
    findpost
    0.38
    TabIndex
    0.38
    ActionCreators
    0.38
    Activations Density 0.423%

    No Known Activations