© 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. 20-GEMMASCOPE-RES-131K
    11. 121716
    Prev
    Next
    INDEX
    Explanations

    details related to album releases and artist information

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

    new album releases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tė
    -0.46
    mybatisplus
    -0.45
     ansvar
    -0.39
    tagHelperRunner
    -0.38
     veiks
    -0.36
    SerializedSize
    -0.35
     obsługi
    -0.34
     estudante
    -0.33
     bestimm
    -0.33
     prefeitura
    -0.33
    POSITIVE LOGITS
    TargetException
    0.60
     صوتيه
    0.49
    CPtr
    0.47
    ClientSize
    0.46
     kaarangay
    0.46
    Последние
    0.45
    StoryboardSegue
    0.45
    ########.
    0.44
    fare
    0.44
    modern
    0.44
    Activations Density 0.016%

    No Known Activations