© 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 - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 4302
    Prev
    Next
    INDEX
    Explanations

    file path references

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

    File paths and directories

    np_acts-logits-general · gemini-2.0-flash

    file paths

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     enfans
    -0.47
    래스
    -0.46
     ſtre
    -0.45
    liferay
    -0.43
    ONESIA
    -0.43
     avoient
    -0.42
    httphttps
    -0.42
     feroit
    -0.41
     pouvoit
    -0.41
     anſ
    -0.41
    POSITIVE LOGITS
     ['./
    1.13
     './
    0.86
     "./
    0.84
    ("./
    0.81
    ('./
    0.80
    ="./
    0.79
     './../
    0.76
     AssemblyVersion
    0.75
    "./
    0.74
     ./
    0.72
    Activations Density 0.024%

    No Known Activations