© 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. 18-GEMMASCOPE-RES-16K
    11. 2975
    Prev
    Next
    INDEX
    Explanations

    terms related to identification and discovery processes

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

    "Identified" followed by a preposition

    np_acts-logits-general · gemini-2.0-flash

    identifying things as/with/from

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    떨
    -0.56
    die
    -0.55
    omány
    -0.50
     adelante
    -0.49
     
    -0.48
    dy
    -0.48
    C
    -0.48
    גרת
    -0.46
    w
    -0.46
     T
    -0.46
    POSITIVE LOGITS
     itſelf
    1.08
     myſelf
    1.08
    '},
    1.03
    '));
    1.01
     Efq
    1.01
     purpoſe
    1.00
    ")));
    0.95
    '],
    0.93
    "],
    0.93
    writeFieldEnd
    0.92
    Activations Density 0.296%

    No Known Activations