© 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. 10700
    Prev
    Next
    INDEX
    Explanations

    terms related to alternatives or alternative options

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

    "alternative"

    np_acts-logits-general · gemini-2.0-flash

    alternative concepts or arrangements

    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
    agoza
    -0.64
    InputBorder
    -0.55
    #+#
    -0.55
    verläs
    -0.52
     gră
    -0.49
    animous
    -0.49
     voluto
    -0.49
    tagHelperRunner
    -0.48
    nps
    -0.48
    Przypisy
    -0.47
    POSITIVE LOGITS
     Alternative
    1.08
    Alternative
    1.04
    Alternatives
    0.98
     Alternate
    0.98
     ALTERN
    0.96
     Alternatives
    0.96
     alternative
    0.92
    ALTERN
    0.90
     ALTERNATIVE
    0.89
    Alternate
    0.88
    Activations Density 0.058%

    No Known Activations