© 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. 23-GEMMASCOPE-RES-16K
    6. 14724
    Prev
    Next
    INDEX
    Explanations

    descriptive phrases concerning condition and maintenance of objects, particularly highlighting quality and repair status

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    secuencias
    -0.58
    esModule
    -0.58
     henvisninger
    -0.50
    UnknownFieldSet
    -0.50
    entyfik
    -0.49
    migrationBuilder
    -0.49
    ftagPool
    -0.49
     estrictamente
    -0.48
     strictement
    -0.48
     potes
    -0.47
    POSITIVE LOGITS
     condition
    1.78
     shape
    1.59
    condition
    1.46
     Condition
    1.42
    Condition
    1.31
     CONDITION
    1.29
     Shape
    1.27
    shape
    1.25
     SHAPE
    1.17
    CONDITION
    1.13
    Activations Density 0.151%

    No Known Activations