© 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. 14-GEMMASCOPE-RES-16K
    6. 7794
    Prev
    Next
    INDEX
    Explanations

    terms related to classification and evaluation in documents

    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
    DOCTYPE
    -0.58
     szóci
    -0.56
    asih
    -0.56
    gisi
    -0.55
     connaissent
    -0.55
     Pristupljeno
    -0.53
    ChildIndex
    -0.52
     sélectionné
    -0.52
    XmlIgnore
    -0.51
    Auswahl
    -0.50
    POSITIVE LOGITS
    DockStyle
    0.68
     صوتيه
    0.56
    __*/
    0.56
     noqa
    0.56
     ligiloj
    0.55
     favored
    0.54
     ErrIntOverflow
    0.54
     '\\;'
    0.53
    fromnode
    0.53
     essential
    0.52
    Activations Density 0.842%

    No Known Activations