© 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-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 7800
    Prev
    Next
    INDEX
    Explanations

    Java package and import statements

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

    "import" statements and package names

    np_acts-logits-general · gemini-2.0-flash

    programming language imports

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
     InputDecoration
    -0.59
    addCriterion
    -0.57
    GeoNames
    -0.56
    principalColumn
    -0.55
     AssemblyCulture
    -0.53
    MessageOf
    -0.53
     ролях
    -0.52
     trasparente
    -0.51
     tages
    -0.51
     SQLAlchemy
    -0.51
    POSITIVE LOGITS
     static
    0.90
     java
    0.74
    triangleq
    0.60
     universale
    0.59
    //*/
    0.59
    })));
    0.59
     Clarkson
    0.58
    ]";
    0.58
    bibinfo
    0.57
     org
    0.57
    Activations Density 0.026%

    No Known Activations