© 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. 7650
    Prev
    Next
    INDEX
    Explanations

    information about player transfers and game updates

    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
    599
    +0.34
    1.3%
    1577
    +0.31
    1.2%
    764
    +0.18
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    764
    +0.34
    0.10
    599
    +0.31
    0.12
    1009
    +0.18
    0.05
    Negative Logits
     gmbh
    -0.72
     gawas
    -0.67
     snippetHide
    -0.62
     utah
    -0.59
    relenting
    -0.56
     venezuela
    -0.53
    Externé
    -0.53
     ziua
    -0.53
     nevada
    -0.52
     munich
    -0.52
    POSITIVE LOGITS
    SaveChangesAsync
    0.47
     Treiber
    0.47
    ActionCreators
    0.47
    baomidou
    0.46
     médic
    0.45
    SaveSave
    0.43
     AudioSource
    0.43
    SpringRunner
    0.41
     Schwier
    0.40
    intios
    0.39
    Activations Density 2.300%

    No Known Activations