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. 7-GEMMASCOPE-RES-16K
    6. 9222
    Prev
    Next
    INDEX
    Explanations

    instances of recorded actions or entries in a formal context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ikian
    -0.47
     -
    -0.44
    QueryParam
    -0.44
    componentWill
    -0.44
     közül
    -0.44
     klap
    -0.43
     Aussch
    -0.42
    ClientSize
    -0.42
    Dougall
    -0.42
     Har
    -0.42
    POSITIVE LOGITS
    MessageTagHelper
    0.96
    mybatisplus
    0.82
    MigrationBuilder
    0.79
    انيف
    0.79
     bezeichneter
    0.75
     مرئيه
    0.74
     markings
    0.73
    styleType
    0.73
     scri
    0.73
     صوتيه
    0.72
    Activations Density 0.231%

    No Known Activations