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. 18-GEMMASCOPE-RES-16K
    6. 4090
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal implications of race and evidence in criminal cases

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

    negation or absence of something

    np_acts-logits-general · gemini-2.0-flash

    hydrogen bond

    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
    SequentialGroup
    -0.70
    AndGet
    -0.66
     autorytatywna
    -0.62
    rather
    -0.56
     plutôt
    -0.55
    сього
    -0.54
    instead
    -0.54
    PhysRev
    -0.53
    gatsby
    -0.52
    adaptiveStyles
    -0.52
    POSITIVE LOGITS
     anymore
    2.00
     nor
    1.99
     any
    1.89
     anything
    1.89
     quelconque
    1.58
    anything
    1.57
     żad
    1.46
    有任何
    1.44
    任何
    1.42
     apapun
    1.41
    Activations Density 1.386%

    No Known Activations