Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 1-GEMMASCOPE-RES-16K
    6. 9521
    Prev
    Next
    INDEX
    Explanations

    specific recurring elements related to value, particularly in the context of assumptions or claims made in a text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <?
    -0.56
    ributions
    -0.55
    ForRow
    -0.54
    reportWebVitals
    -0.53
    WithIdentifier
    -0.53
    modb
    -0.53
     surla
    -0.52
    ArgsConstructor
    -0.51
     inspiration
    -0.51
    ItemBackground
    -0.51
    POSITIVE LOGITS
    va
    1.08
     Personality
    0.80
     personality
    0.73
    personality
    0.71
    VA
    0.63
    igshid
    0.60
     препратки
    0.60
    Personality
    0.60
     Forum
    0.59
     OP
    0.59
    Activations Density 0.076%

    No Known Activations