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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 14725
    Prev
    Next
    INDEX
    Explanations

    concepts related to the implications and consequences of societal issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ôtel
    -0.54
    AutoField
    -0.51
     استنادى
    -0.50
    IsPostBack
    -0.48
    SpringBootTest
    -0.46
     myſelf
    -0.43
     rhestr
    -0.43
    apunov
    -0.42
     pousada
    -0.42
     LEAGUE
    -0.41
    POSITIVE LOGITS
     collectively
    0.41
    dyž
    0.38
    rungsseite
    0.36
     samot
    0.36
     collective
    0.36
     coe
    0.35
    دانشنامهٔ
    0.33
     kohdetta
    0.33
     pojed
    0.32
    IVEREF
    0.32
    Activations Density 0.629%

    No Known Activations