© 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-2-9B
    4. Residual Stream - 16k
    5. 38-GEMMASCOPE-RES-16K
    6. 15254
    Prev
    Next
    INDEX
    Explanations

    geographic locations and infrastructure references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Geplaatst
    -0.63
     ब्रेकडाउन
    -0.58
    RTSC
    -0.57
     Meksiku
    -0.52
    ConstraintMaker
    -0.51
    IsContent
    -0.47
    󠁥
    -0.43
     صوتيه
    -0.42
    Aholisi
    -0.42
    tonsoft
    -0.41
    POSITIVE LOGITS
     Welsh
    1.59
     Wales
    1.45
    Welsh
    1.42
    Wales
    1.30
     Cardiff
    1.23
     Cymru
    1.20
    Cardiff
    1.10
     Llan
    1.09
     wales
    1.08
    wales
    1.06
    Activations Density 0.232%

    No Known Activations