© 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. 24-GEMMASCOPE-RES-16K
    11. 14339
    Prev
    Next
    INDEX
    Explanations

    data structures related to user groups and their properties

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

    Key-value pairs and array indexing

    np_acts-logits-general · gemini-2.0-flash

    Count me in sugar

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    </h3>
    -1.18
    </h6>
    -0.93
    ）』
    -0.65
    <h4>
    -0.59
    '>
    -0.58
    mybatisplus
    -0.52
    pushFollow
    -0.52
    ResumeLayout
    -0.52
    :✨
    -0.50
    GEBURTSDATUM
    -0.50
    POSITIVE LOGITS
    ".
    2.52
    ."
    2.51
    ",
    2.51
    ";
    2.33
    "}
    2.27
    "
    2.26
    ")
    2.25
    "
    2.24
    !"
    2.22
    ?"
    2.21
    Activations Density 3.777%

    No Known Activations