© 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-2-2B
    7. Residual Stream - 16k
    9. 14-GEMMASCOPE-RES-16K
    11. 4539
    Prev
    Next
    INDEX
    Explanations

    indicators of the beginning of a new segment or important section in a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     the
    -0.41
    opra
    -0.41
     sanitarios
    -0.41
    mouseout
    -0.40
     some
    -0.40
     The
    -0.39
     gaan
    -0.38
     برانيه
    -0.38
     both
    -0.38
     anfangen
    -0.38
    POSITIVE LOGITS
    ConstraintMaker
    1.08
    Personendaten
    0.86
    StoryboardSegue
    0.86
    SourceChecksum
    0.83
    GEBURTSDATUM
    0.83
     cherchés
    0.78
     propOrder
    0.77
    IntoConstraints
    0.76
    ]")]
    0.73
    principalColumn
    0.73
    Activations Density 0.814%

    No Known Activations