Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 24-GEMMASCOPE-RES-16K
    6. 14043
    Prev
    Next
    INDEX
    Explanations

    phrases related to ease of use and simplicity

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

    Followed by a verb

    np_acts-logits-general · gemini-2.0-flash

    easy to perform actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IBOutlet
    -0.78
     autorytatywna
    -0.74
    +#+#
    -0.69
     ProtoMessage
    -0.68
     ModelExpression
    -0.67
    AutoScaleMode
    -0.66
    AccessorTable
    -0.66
     disambiguazione
    -0.65
     jadx
    -0.65
    ########.
    -0.63
    POSITIVE LOGITS
     manage
    0.67
     impossible
    0.65
     manoeuvre
    0.64
     navigate
    0.63
     comprehend
    0.62
     maneuver
    0.62
     digest
    0.60
     handle
    0.60
    navigate
    0.59
     manipulate
    0.58
    Activations Density 0.122%

    No Known Activations