© 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. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 844
    Prev
    Next
    INDEX
    Explanations

    phrases related to contrasting different concepts

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1842
    +0.18
    0.6%
    50
    +0.14
    0.4%
    1806
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1806
    +0.18
    0.07
    50
    +0.14
    0.05
    856
    +0.13
    0.05
    Negative Logits
     دیکھیے
    -0.71
     gyhoeddwyd
    -0.68
     كومونز
    -0.66
     Roskov
    -0.58
    styleType
    -0.58
    HideFlags
    -0.57
     ianuarie
    -0.55
    Geplaatst
    -0.55
    FieldBuilder
    -0.55
     iyon
    -0.54
    POSITIVE LOGITS
     whatnot
    0.72
     Shakspeare
    0.72
     lastly
    0.68
     increa
    0.68
     intersper
    0.68
     ete
    0.66
     &.
    0.66
     Fg
    0.66
     uniqu
    0.66
     Cfr
    0.65
    Activations Density 0.214%

    No Known Activations