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. 17-GEMMASCOPE-RES-16K
    6. 7079
    Prev
    Next
    INDEX
    Explanations

    references to software licensing and legal terms related to distribution

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GEBURTS
    -0.62
    Rhestr
    -0.61
    AutoScaleMode
    -0.60
     StringTokenizer
    -0.60
    MultipartFile
    -0.58
    Portály
    -0.56
    INCLUDES
    -0.56
    XDECREF
    -0.56
     Dickens
    -0.56
    qtype
    -0.55
    POSITIVE LOGITS
    styleUrls
    0.47
     denn
    0.43
    nash
    0.41
     distanciation
    0.41
    verwijspagina
    0.41
     ὅ
    0.39
    deno
    0.38
    <!--
    0.38
    #
    0.38
     successfully
    0.37
    Activations Density 0.050%

    No Known Activations