© 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. 7-GEMMASCOPE-RES-16K
    6. 4713
    Prev
    Next
    INDEX
    Explanations

    elements related to querying and formatting data within a programming 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
    AsUp
    -1.00
     defaultstate
    -0.97
    RenderAtEndOf
    -0.97
    Rhestr
    -0.86
    tagHelperRunner
    -0.85
    WebVitals
    -0.84
     AssemblyTitle
    -0.84
    stdc
    -0.83
    complexType
    -0.83
     Paglinawan
    -0.81
    POSITIVE LOGITS
    Params
    0.42
     бы
    0.40
     پیش
    0.39
    ರು
    0.38
    Variables
    0.38
    Arguments
    0.36
    Template
    0.36
    default
    0.35
    Pron
    0.35
    Position
    0.34
    Activations Density 0.215%

    No Known Activations