© 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. 2941
    Prev
    Next
    INDEX
    Explanations

    expressions related to forward-looking statements and projections

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

    "forward"

    np_acts-logits-general · gemini-2.0-flash

    forward-looking statements

    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
     Roskov
    -0.81
    RTGC
    -0.78
    awtextra
    -0.70
    +#+#
    -0.70
    HideFlags
    -0.70
    featureID
    -0.70
    tagHelperRunner
    -0.70
     ModelExpression
    -0.69
    onAttach
    -0.69
     initComponents
    -0.69
    POSITIVE LOGITS
     Forward
    0.90
    Forward
    0.88
    FORWARD
    0.88
     forwards
    0.88
     FORWARD
    0.84
     forward
    0.82
    forward
    0.79
    ward
    0.73
    wards
    0.65
    WARDS
    0.62
    Activations Density 0.172%

    No Known Activations