© 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. 4-GEMMASCOPE-RES-16K
    6. 10801
    Prev
    Next
    INDEX
    Explanations

    phrases or clauses that indicate possession or relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ^(@)
    -1.26
     doubtnut
    -1.13
     -"
    -1.10
     poffible
    -1.09
     '"
    -1.09
     Jefus
    -1.08
     pleaf
    -1.08
    。"
    -1.07
     Majefty
    -1.07
     Chrift
    -1.06
    POSITIVE LOGITS
     “
    1.86
    ’
    1.82
    ”
    1.73
     ‘
    1.69
    ’,
    1.67
    ’.
    1.60
    .’
    1.56
    “
    1.56
    ,’
    1.50
    ”,
    1.48
    Activations Density 0.718%

    No Known Activations