© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 3394
    Prev
    Next
    INDEX
    Explanations

    legal terminology and concepts related to charges and threats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Threats or negative consequences

    np_acts-logits-general · gemini-2.0-flash

    contingent negative outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Obrázky
    -0.64
    новништво
    -0.57
    KommentareTeilen
    -0.48
    ScreenState
    -0.47
    }();
    -0.46
    ContextHolder
    -0.46
    poved
    -0.46
    श्न
    -0.46
    __':
    -0.45
    `{.
    -0.43
    POSITIVE LOGITS
     unless
    2.13
    unless
    1.82
     Unless
    1.72
    Unless
    1.66
     if
    1.40
    如果不
    1.19
    除非
    1.15
     nếu
    1.11
     если
    1.04
     hvis
    1.03
    Activations Density 0.335%

    No Known Activations